{"id":"https://openalex.org/W4416252396","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227906","title":"Data-efficient LLM Fine-tuning for Code Generation","display_name":"Data-efficient LLM Fine-tuning for Code Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252396","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227906"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033940457","display_name":"Weijie Lv","orcid":"https://orcid.org/0000-0001-8269-9641"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weijie Lv","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000758800","display_name":"Xuan Xia","orcid":"https://orcid.org/0000-0002-0118-7482"},"institutions":[{"id":"https://openalex.org/I4210104064","display_name":"Shenzhen Academy of Robotics","ror":"https://ror.org/01h027j09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210104064"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Xia","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society,Shenzhen,China","institution_ids":["https://openalex.org/I4210104064"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103204774","display_name":"Sheng-Jun Huang","orcid":"https://orcid.org/0000-0002-7673-5367"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng-Jun Huang","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033940457"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":3.0965,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94094653,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.2240999937057495,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.2240999937057495,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.12800000607967377,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.09830000251531601,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5975000262260437},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5386000275611877},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39750000834465027},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3935999870300293},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3928000032901764},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.38589999079704285},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3643999993801117},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.36090001463890076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836899995803833},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5386000275611877},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4577000141143799},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3928000032901764},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C165435473","wikidata":"https://www.wikidata.org/wiki/Q1509884","display_name":"Padding","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29820001125335693},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2970641574","https://openalex.org/W4252326246","https://openalex.org/W4385572634","https://openalex.org/W4390871903","https://openalex.org/W4401042981","https://openalex.org/W4401043205","https://openalex.org/W4402670193","https://openalex.org/W4404782488"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"significant":[6],"potential":[7],"in":[8,53],"code":[9],"generation":[10],"tasks.":[11],"However,":[12],"there":[13],"remains":[14],"a":[15,49,98,165],"performance":[16,129,135,193],"gap":[17],"between":[18],"open-source":[19],"and":[20,59,70,106,151,185],"closed-source":[21],"models.":[22],"To":[23],"address":[24],"this":[25,45],"gap,":[26],"existing":[27],"approaches":[28],"typically":[29],"generate":[30],"large":[31],"amounts":[32],"of":[33,61,80,119,130],"synthetic":[34],"data":[35,50,68,183],"for":[36,63],"fine-tuning,":[37],"which":[38,102],"often":[39],"leads":[40],"to":[41,55,148,161],"inefficient":[42],"training.":[43],"In":[44],"work,":[46],"we":[47,92],"propose":[48],"selection":[51,184],"strategy":[52,86],"order":[54],"improve":[56],"the":[57,73,78,81,94,120,123,133,137,152,173,177],"effectiveness":[58],"efficiency":[60],"training":[62,116,141,197],"code-based":[64],"LLMs.":[65],"By":[66,180],"prioritizing":[67],"complexity":[69],"ensuring":[71],"that":[72,114],"sampled":[74],"subset":[75],"aligns":[76],"with":[77,136,172],"distribution":[79],"original":[82],"dataset,":[83,122],"our":[84,187],"sampling":[85],"effectively":[87],"selects":[88],"high-quality":[89],"data.":[90],"Additionally,":[91],"optimize":[93],"tokenization":[95],"process":[96],"through":[97],"\"dynamic":[99],"pack\"":[100],"technique,":[101],"minimizes":[103],"padding":[104],"tokens":[105],"reduces":[107],"computational":[108],"resource":[109],"consumption.":[110],"Experimental":[111],"results":[112],"show":[113],"when":[115],"on":[117,176],"40%":[118],"OSS-Instruct":[121],"DeepSeek-Coder-Base-6.7B":[124],"model":[125,175,192],"achieves":[126],"an":[127],"average":[128],"66.9%,":[131],"surpassing":[132],"66.1%":[134],"full":[138],"dataset.":[139,179],"Moreover,":[140],"time":[142],"is":[143],"reduced":[144],"from":[145,158],"47":[146],"minutes":[147],"34":[149],"minutes,":[150],"peak":[153],"GPU":[154],"memory":[155],"usage":[156],"decreases":[157],"61.47":[159],"GB":[160,163],"42.72":[162],"during":[164],"single":[166],"epoch.":[167],"Similar":[168],"improvements":[169],"are":[170],"observed":[171],"CodeLlama-Python-7B":[174],"Evol-Instruct":[178],"optimizing":[181],"both":[182],"tokenization,":[186],"approach":[188],"not":[189],"only":[190],"improves":[191],"but":[194],"also":[195],"enhances":[196],"efficiency.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}